使用blas做矩阵乘法

#define min(x,y) (((x) < (y)) ? (x) : (y))

#include <stdio.h>
#include <stdlib.h>
#include <cublas_v2.h>
#include <iostream>
#include <vector>
//extern "C"
//{
   #include <cblas.h>
//}

using namespace std;
int main()
{

    const enum CBLAS_ORDER Order=CblasRowMajor;
    const enum CBLAS_TRANSPOSE TransA=CblasNoTrans;
    const enum CBLAS_TRANSPOSE TransB=CblasNoTrans;
    const int M=;//A的行数，C的行数
    const int N=;//B的列数，C的列数
    const int K=;//A的列数，B的行数
    const float alpha=;
    const float beta=;
    const int lda=K;//A的列
    const int ldb=N;//B的列
    const int ldc=N;//C的列
    const float A[M*K]={,,,,,,,,,,,};
    const float B[K*N]={,,,,,};
    float C[M*N];

    cblas_sgemm(Order, TransA, TransB, M, N, K, alpha, A, lda, B, ldb, beta, C, ldc);

    for(int i=;i<M;i++)
    {
       for(int j=;j<N;j++)
       {
           cout<<C[i*N+j]<<"\n";
       }
       cout<<endl;
    }

    return EXIT_SUCCESS;

}

g++ testblas.c++ -lopenblas  -o testout

g++ testblas.c++ -lopenblas_piledriverp-r0.2.9 -o testout   本地编译openblas版本

注意library放在引用library的函数的后面

cblas_sgemm

Multiplies two matrices (single-precision).

void cblas_sgemm (
const enum CBLAS_ORDER Order,  // Specifies row-major (C) or column-major (Fortran) data ordering.
//typedef enum CBLAS_ORDER     {CblasRowMajor=101, CblasColMajor=102} CBLAS_ORDER;

const enum CBLAS_TRANSPOSE TransA,//Specifies whether to transpose matrix A.
const enum CBLAS_TRANSPOSE TransB,
const int M,   //Number of rows in matrices A and C.
const int N,//Number of rows in matrices A and C.
const int K,  //Number of columns in matrix A; number of rows in matrix B
const float alpha, //Scaling factor for the product of matrices A and B
const float *A,
const int lda, //The size of the first dimention of matrix A; if you are passing a matrix A[m][n], the value should be m.  stride

lda, ldb and ldc (the strides) are not relevant to my problem after all, but here's an explanation of them : 

The elements of a matrix (i.e a 2D array) are stored contiguously in memory. However, they may be stored in either column-major or row-major fashion. The stride represents the distance in memory between elements in adjacent rows (if row-major) or in adjacent columns (if column-major). This means that the stride is usually equal to the number of rows/columns in the matrix.

Matrix A =
[1 2 3]
[4 5 6]
Row-major stores values as {1,2,3,4,5,6}
Stride here is 3

Col-major stores values as {1, 4, 2, 5, 3, 6}
Stride here is 2

Matrix B =
[1 2 3]
[4 5 6]
[7 8 9]

Col-major storage is {1, 4, 7, 2, 5, 8, 3, 6, 9}
Stride here is 3

Read more: http://www.physicsforums.com 
const float *B,
const int ldb,  //The size of the first dimention of matrix B; if you are passing a matrix B[m][n], the value should be m.
const float beta,  //Scaling factor for matrix C.
float *C,
const int ldc    //The size of the first dimention of matrix C; if you are passing a matrix C[m][n], the value should be m.
);

Thus, it calculates either
C←αAB + βC
or
C←αBA + βC
with optional use of transposed forms of A, B, or both.

typedef enum CBLAS_ORDER     {CblasRowMajor=101, CblasColMajor=102} CBLAS_ORDER;
typedef enum CBLAS_TRANSPOSE {CblasNoTrans=111, CblasTrans=112, CblasConjTrans=113, CblasConjNoTrans=114} CBLAS_TRANSPOSE;

$C=A*B$

$C^T=(A*B)^T=B^T*A^T$  把A和B的顺序颠倒，可以直接得到转制矩阵乘法的结果，不用作其他变换，（结果C也是转制）。

Y←αAX + βY

cblas_sgemv
Multiplies a matrix by a vector (single precision).

void cblas_sgemv (
const enum CBLAS_ORDER Order,
const enum CBLAS_TRANSPOSE TransA,
const int M,
const int N,
const float alpha,
const float *A,
const int lda,
const float *X,
const int incX,
const float beta,
float *Y,
const int incY
);

STL版本

cblas_daxpy
Computes a constant times a vector plus a vector (double-precision).　　

On return, the contents of vector Y are replaced with the result. The value computed is (alpha * X[i]) +
Y[i].

#include <OpenBlas/cblas.h>
#include <OpenBlas/common.h>
#include <iostream>
#include <vector>

int main()
{
    blasint n = ;
    blasint in_x =;
    blasint in_y =;

    std::vector<double> x(n);
    std::vector<double> y(n);

    double alpha = ;

    std::fill(x.begin(),x.end(),1.0);
    std::fill(y.begin(),y.end(),2.0);

    cblas_daxpy( n, alpha, &x[], in_x, &y[], in_y);

    //Print y
    for(int j=;j<n;j++)
        std::cout << y[j] << "\t";

    std::cout << std::endl;
}

cublas

cublasStatus_t
cublasCreate(cublasHandle_t *handle)

Return Value Meaning
CUBLAS_STATUS_SUCCESS the initialization succeeded
CUBLAS_STATUS_NOT_INITIALIZED the CUDATM Runtime initialization failed
CUBLAS_STATUS_ALLOC_FAILED the resources could not be allocated

cublasStatus_t
cublasDestroy(cublasHandle_t handle)

Return Value Meaning
CUBLAS_STATUS_SUCCESS the shut down succeeded
CUBLAS_STATUS_NOT_INITIALIZED the library was not initialized

cublasStatus_t cublasSgemm(cublasHandle_t handle,  // 唯一的不同：handle to the cuBLAS library context.

cublasOperation_t transa,
 cublasOperation_t transb
int m,
 int n, 
int k,
const float *alpha,
const float*A, 
int lda,
const float*B, 
int ldb,
const float*beta,
float*C,
 int ldc
)

void cblas_sgemm (
const enum CBLAS_ORDER Order,  // Specifies row-major (C) or column-major (Fortran) data ordering.
//typedef enum CBLAS_ORDER     {CblasRowMajor=101, CblasColMajor=102} CBLAS_ORDER;

const enum CBLAS_TRANSPOSE TransA,//Specifies whether to transpose matrix A.
const enum CBLAS_TRANSPOSE TransB,
const int M,   //Number of rows in matrices A and C.
const int N,//Number of rows in matrices A and C.
const int K,  //Number of columns in matrix A; number of rows in matrix B
const float alpha, //Scaling factor for the product of matrices A and B
const float *A,
const int lda, //The size of the first dimention of matrix A; if you are passing a matrix A[m][n], the value should be m.
const float *B,
const int ldb,  //The size of the first dimention of matrix B; if you are passing a matrix B[m][n], the value should be m.
const float beta,  //Scaling factor for matrix C.
float *C,
const int ldc    //The size of the first dimention of matrix C; if you are passing a matrix C[m][n], the value should be m.
);